© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6631
    Prev
    Next
    INDEX
    Explanations

    action phrases used to direct the reader to more resources

    oai_token-act-pair · gemini-2.0-flash

    Directing to external resource

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.83
     désolés
    -0.78
    ValueGeneration
    -0.77
    rungsseite
    -0.71
    makeConstraints
    -0.71
    extAlignment
    -0.71
     ModelAndView
    -0.67
    getSystemService
    -0.66
     MainAxisSize
    -0.66
     GenerationType
    -0.65
    POSITIVE LOGITS
     our
    0.73
     my
    0.65
     My
    0.58
     the
    0.50
    My
    0.46
    oph
    0.46
     their
    0.45
     this
    0.43
     more
    0.42
    Izvori
    0.42
    Activations Density 5.009%

    No Known Activations